Leptospirosis modelling using hydrometeorological indices and random forest machine learning

• Published in: International journal of biometeorology 2023-03, Vol.67 (3), p.423-437
• Main Authors: Jayaramu, Veianthan, Zulkafli, Zed, De Stercke, Simon, Buytaert, Wouter, Rahmat, Fariq, Abdul Rahman, Ribhan Zafira, Ishak, Asnor Juraiza, Tahir, Wardah, Ab Rahman, Jamalludin, Mohd Fuzi, Nik Mohd Hafiz
• Format: Article
• Language: English
• Subjects: Animal Physiology; Annual rainfall; Automobile Driving; Biological and Medical Physics; Biophysics; Climate change; Climatic indexes; Correlation analysis; Cross correlation; Earth and Environmental Science; Environment; Environmental Health; Extreme weather; Humans; Hydrometeorological data; Hydrometeorology; Leptospirosis; Leptospirosis - epidemiology; Machine learning; Meteorology; Model accuracy; Modelling; Monsoon rainfall; Monsoons; Original Paper; Plant Physiology; Predictions; Rainfall; Random Forest; Relative humidity; Seasonal variations; Seasons; Stream discharge; Stream flow; Temperature; Time lag; Water levels
• ISSN: 0020-7128; 1432-1254
• DOI: 10.1007/s00484-022-02422-y

Leptospirosis is a zoonosis that has been linked to hydrometeorological variability. Hydrometeorological averages and extremes have been used before as drivers in the statistical prediction of disease. However, their importance and predictive capacity are still little known. In this study, the use of a random forest classifier was explored to analyze the relative importance of hydrometeorological indices in developing the leptospirosis model and to evaluate the performance of models based on the type of indices used, using case data from three districts in Kelantan, Malaysia, that experience annual monsoonal rainfall and flooding. First, hydrometeorological data including rainfall, streamflow, water level, relative humidity, and temperature were transformed into 164 weekly average and extreme indices in accordance with the Expert Team on Climate Change Detection and Indices (ETCCDI). Then, weekly case occurrences were classified into binary classes “high” and “low” based on an average threshold. Seventeen models based on “average,” “extreme,” and “mixed” indices were trained by optimizing the feature subsets based on the model computed mean decrease Gini (MDG) scores. The variable importance was assessed through cross-correlation analysis and the MDG score. The average and extreme models showed similar prediction accuracy ranges (61.5–76.1% and 72.3–77.0%) while the mixed models showed an improvement (71.7–82.6% prediction accuracy). An extreme model was the most sensitive while an average model was the most specific. The time lag associated with the driving indices agreed with the seasonality of the monsoon. The rainfall variable (extreme) was the most important in classifying the leptospirosis occurrence while streamflow was the least important despite showing higher correlations with leptospirosis.